Abhishek Cauligi

Abhishek Cauligi


Abhishek is a PhD. candidate in Aeronautics and Astronautics. He received a BS in Aerospace Engineering from the University of Michigan in 2016 and an M.S. in Aeronautics & Astronautics from Stanford in 2018. Prior to Stanford, Abhishek interned with the GNC group at SpaceX and the ADCS group at Planetary Resources.

Abhishek’s current research interests entail combining tools from trajectory optimization, optimal control, and machine learning towards problems in spacecraft robotics and systems with contact. In addition, he has worked on running experiments on the International Space Station with the Astrobee robot for grasping and control using gecko-inspired adhesives.

In his free time, Abhishek likes watching movies, learning German, and playing tennis.

Awards:

  • 2016 NASA Space Technology Research Fellowship

ASL Publications

  1. A. Cauligi, P. Culbertson, E. Schmerling, M. Schwager, B. Stellato, and M. Pavone, “CoCo: Online Mixed-Integer Control via Supervised Learning,” IEEE Robotics and Automation Letters, 2021. (Submitted)

    Abstract: Many robotics problems, from robot motion planning to object manipulation, can be modeled as mixed-integer convex programs (MICPs). However, state-of-the-art algorithms are still unable to solve MICPs for control problems quickly enough for online use and existing heuristics can typically only find suboptimal solutions that might degrade robot performance. In this work, we turn to data-driven methods and present the Combinatorial Offline, Convex Online (CoCo) algorithm for quickly finding high quality solutions for MICPs. CoCo consists of a two-stage approach. In the offline phase, we train a neural network classifier that maps the problem parameters to a (logical strategy), which we define as the discrete arguments and relaxed big-M constraints associated with the optimal solution for that problem. Online, the classifier is applied to select a candidate logical strategy given new problem parameters; applying this logical strategy allows us to solve the original MICP as a convex optimization problem. We show through numerical experiments how CoCo finds near optimal solutions to MICPs arising in robot planning and control with 1 to 2 orders of magnitude solution speedup compared to other data-driven approaches and solvers.

    @article{CauligiCulbertsonEtAl2021,
      author = {Cauligi, A. and Culbertson, P. and Schmerling, E. and Schwager, M. and Stellato, B. and Pavone, M.},
      title = {{CoCo}: Online Mixed-Integer Control via Supervised Learning},
      journal = {{IEEE Robotics and Automation Letters}},
      year = {2021},
      note = {Submitted},
      url = {http://arxiv.org/abs/2107.08143},
      keywords = {sub},
      owner = {acauligi},
      timestamp = {2021-07-20}
    }
    
  2. T. G. Chen, A. Cauligi, S. A. Suresh, M. Pavone, and M. R. Cutkosky, “Testing Gecko-Inspired Adhesives with Astrobee Aboard the ISS,” IEEE Robotics and Automation Magazine, 2021. (Submitted)

    Abstract:

    @article{ChenCauligiEtAl2021,
      author = {Chen, T. G. and Cauligi, A. and Suresh, S. A. and Pavone, M. and Cutkosky, M. R.},
      title = {Testing Gecko-Inspired Adhesives with {Astrobee} Aboard the {ISS}},
      journal = {{IEEE Robotics and Automation Magazine}},
      year = {2021},
      keywords = {sub},
      owner = {acauligi},
      timestamp = {2021-11-02}
    }
    
  3. A. Cauligi, T. Chen, S. A. Suresh, M. Dille, R. G. Ruiz, A. M. Vargas, M. Pavone, and M. R. Cutkosky, “Design and Development of a Gecko-Adhesive Gripper for the Astrobee Free-Flying Robot,” in Int. Symp. on Artificial Intelligence, Robotics and Automation in Space, Pasadena, California, 2020.

    Abstract: Assistive free-flying robots are a promising platform for supporting and working alongside astronauts in carrying out tasks that require interaction with the environment. However, current free-flying robot platforms are limited by existing manipulation technologies in being able to grasp and manipulate surrounding objects. Instead, gecko-inspired adhesives offer many advantages for an alternate grasping and manipulation paradigm for use in assistive free-flyer applications. In this work, we present the design of a gecko-inspired adhesive gripper for performing perching and grasping maneuvers for the Astrobee robot, a free-flying robot currently operating on-board the International Space Station. We present software and hardware integration details for the gripper units that were launched to the International Space Station in 2019 for in-flight experiments with Astrobee. Finally, we present preliminary results for on-ground experiments conducted with the gripper and Astrobee on a free-floating spacecraft test bed.

    @inproceedings{CauligiChenEtAl2020,
      author = {Cauligi, A. and Chen, T. and Suresh, S. A. and Dille, M. and Ruiz, R. G. and Vargas, A. M. and Pavone, M. and Cutkosky, M. R.},
      title = {Design and Development of a Gecko-Adhesive Gripper for the {Astrobee} Free-Flying Robot},
      booktitle = {{Int. Symp. on Artificial Intelligence, Robotics and Automation in Space}},
      year = {2020},
      address = {Pasadena, California},
      month = oct,
      url = {https://arxiv.org/pdf/2009.09151.pdf},
      owner = {acauligi},
      timestamp = {2020-09-18}
    }
    
  4. A. Cauligi, P. Culbertson, B. Stellato, D. Bertsimas, M. Schwager, and M. Pavone, “Learning Mixed-Integer Convex Optimization Strategies for Robot Planning and Control,” in Proc. IEEE Conf. on Decision and Control, Jeju Island, Republic of Korea, 2020. (In Press)

    Abstract: Mixed-integer convex programming (MICP) has seen significant algorithmic and hardware improvements with several orders of magnitude solve time speedups compared to 25 years ago. Despite these advances, MICP has been rarely applied to real-world robotic control because the solution times are still too slow for online applications. In this work, we extend the machine learning optimizer (MLOPT) framework to solve MICPs arising in robotics at very high speed. MLOPT encodes the combinatorial part of the optimal solution into a strategy. Using data collected from offline problem solutions, we train a multiclass classifier to predict the optimal strategy given problem-specific parameters such as states or obstacles. Compared to previous approaches, we use task-specific strategies and prune redundant ones to significantly reduce the number of classes the predictor has to select from, thereby greatly improving scalability. Given the predicted strategy, the control task becomes a small convex optimization problem that we can solve in milliseconds. Numerical experiments on a cart-pole system with walls, a free-flying space robot and task-oriented grasps show that our method provides not only 1 to 2 orders of magnitude speedups compared to state-of-the-art solvers but also performance close to the globally optimal MICP solution.

    @inproceedings{CauligiCulbertsonEtAl2020,
      author = {Cauligi, A. and Culbertson, P. and Stellato, B. and Bertsimas, D. and Schwager, M. and Pavone, M.},
      title = {Learning Mixed-Integer Convex Optimization Strategies for Robot Planning and Control},
      booktitle = {{Proc. IEEE Conf. on Decision and Control}},
      year = {2020},
      note = {In Press},
      address = {Jeju Island, Republic of Korea},
      month = mar,
      url = {https://arxiv.org/pdf/2004.03736.pdf},
      keywords = {press},
      owner = {acauligi},
      timestamp = {2020-04-05}
    }
    
  5. R. Bonalli, A. Bylard, A. Cauligi, T. Lew, and M. Pavone, “Trajectory Optimization on Manifolds: A Theoretically-Guaranteed Embedded Sequential Convex Programming Approach,” in Robotics: Science and Systems, Freiburg im Breisgau, Germany, 2019.

    Abstract: Sequential Convex Programming (SCP) has recently gain popularity as a tool for trajectory optimization, due to its sound theoretical properties and practical performance. Yet, most SCP-based methods for trajectory optimization are restricted to Euclidean settings, which precludes their application to problem instances where one needs to reason about manifold-type constraints (that is, constraints, such as loop closure, which restrict the motion of a system to a subset of the ambient space). The aim of this paper is to fill this gap by extending SCP-based trajectory optimization methods to a manifold setting. The key insight is to leverage geometric embeddings to lift a manifold-constrained trajectory optimization problem into an equivalent problem defined over a space enjoying Euclidean structure. This insight allows one to extend existing SCP methods to a manifold setting in a fairly natural way. In particular, we present an SCP algorithm for manifold problems with theoretical guarantees that resemble those derived for the Euclidean setting, and demonstrate its practical performance via numerical experiments.

    @inproceedings{BonalliBylardEtAl2019,
      author = {Bonalli, R. and Bylard, A. and Cauligi, A. and Lew, T. and Pavone, M.},
      title = {Trajectory Optimization on Manifolds: {A} Theoretically-Guaranteed Embedded Sequential Convex Programming Approach},
      booktitle = {{Robotics: Science and Systems}},
      year = {2019},
      address = {Freiburg im Breisgau, Germany},
      month = jun,
      url = {https://arxiv.org/pdf/1905.07654.pdf},
      owner = {bylard},
      timestamp = {2019-05-01}
    }
    
  6. R. Bonalli, A. Cauligi, A. Bylard, and M. Pavone, “GuSTO: Guaranteed Sequential Trajectory Optimization via Sequential Convex Programming,” in Proc. IEEE Conf. on Robotics and Automation, Montreal, Canada, 2019.

    Abstract: Sequential Convex Programming (SCP) has recently seen a surge of interest as a tool for trajectory optimization. Yet, most available methods lack rigorous performance guarantees and are often tailored to specific optimal control setups. In this paper, we present GuSTO (Guaranteed Sequential Trajectory Optimization), an algorithmic framework to solve trajectory optimization problems for control-affine systems with drift. GuSTO generalizes earlier SCP-based methods for trajectory optimization (by addressing, for example, goal region constraints and problems with either fixed or free final time), and enjoys theoretical convergence guarantees in terms of convergence to, at least, a stationary point. The theoretical analysis is further leveraged to devise an accelerated implementation of GuSTO, which originally infuses ideas from indirect optimal control into an SCP context. Numerical experiments on a variety of trajectory optimization setups show that GuSTO generally outperforms current state-of-the-art approaches in terms of success rates, solution quality, and computation times.

    @inproceedings{BonalliCauligiEtAl2019,
      author = {Bonalli, R. and Cauligi, A. and Bylard, A. and Pavone, M.},
      title = {{GuSTO:} Guaranteed Sequential Trajectory Optimization via Sequential Convex Programming},
      booktitle = {{Proc. IEEE Conf. on Robotics and Automation}},
      year = {2019},
      address = {Montreal, Canada},
      month = may,
      url = {https://arxiv.org/pdf/1903.00155.pdf},
      owner = {bylard},
      timestamp = {2018-10-04}
    }